WO2013086580A1 - Procédé et appareil d'évaluation d'images médicales - Google Patents

Procédé et appareil d'évaluation d'images médicales Download PDF

Info

Publication number
WO2013086580A1
WO2013086580A1 PCT/AU2012/001536 AU2012001536W WO2013086580A1 WO 2013086580 A1 WO2013086580 A1 WO 2013086580A1 AU 2012001536 W AU2012001536 W AU 2012001536W WO 2013086580 A1 WO2013086580 A1 WO 2013086580A1
Authority
WO
WIPO (PCT)
Prior art keywords
templates
pet
candidate
series
brain
Prior art date
Application number
PCT/AU2012/001536
Other languages
English (en)
Inventor
Vincent DORÉ
Olivier Salvado
Nicholas Delanie Hirst Dowson
Jurgen MEJAN-FRIPP
Christopher Rowe
Victor VILLEMAGNE
Luping Zhou
Original Assignee
Commonwealth Scientific And Industrial Research Organisation
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from AU2011905242A external-priority patent/AU2011905242A0/en
Application filed by Commonwealth Scientific And Industrial Research Organisation filed Critical Commonwealth Scientific And Industrial Research Organisation
Priority to US14/365,745 priority Critical patent/US9361686B2/en
Priority to AU2012350363A priority patent/AU2012350363B2/en
Priority to EP12857342.5A priority patent/EP2790575B1/fr
Priority to CN201280067975.5A priority patent/CN104093354B/zh
Publication of WO2013086580A1 publication Critical patent/WO2013086580A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G06T7/0014—Biomedical image inspection using an image reference approach
    • G06T7/0016—Biomedical image inspection using an image reference approach involving temporal comparison
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G06T7/0014—Biomedical image inspection using an image reference approach
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
    • G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves 
    • A61B5/055—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves  involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/74—Details of notification to user or communication with user or patient ; user input means
    • A61B5/742—Details of notification to user or communication with user or patient ; user input means using visual displays
    • A61B5/7425—Displaying combinations of multiple images regardless of image source, e.g. displaying a reference anatomical image with a live image
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
    • A61B6/02—Devices for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
    • A61B6/03—Computerised tomographs
    • A61B6/037—Emission tomography
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/5207—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of raw data to produce diagnostic data, e.g. for generating an image
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
    • F04C—ROTARY-PISTON, OR OSCILLATING-PISTON, POSITIVE-DISPLACEMENT MACHINES FOR LIQUIDS; ROTARY-PISTON, OR OSCILLATING-PISTON, POSITIVE-DISPLACEMENT PUMPS
    • F04C2270/00—Control; Monitoring or safety arrangements
    • F04C2270/04—Force
    • F04C2270/041—Controlled or regulated
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10081—Computed x-ray tomography [CT]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10088—Magnetic resonance imaging [MRI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10104—Positron emission tomography [PET]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20212—Image combination
    • G06T2207/20216—Image averaging
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20212—Image combination
    • G06T2207/20221—Image fusion; Image merging
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30016—Brain

Definitions

  • the present invention relates to the field of interpretation and processing of medical images and, in particular, discloses a method and system for the interpretation of marker take up in images such as Positron Emission Tomography (PET) images or Single-photon emission computed tomography images (SPECT) for the detection of anomalies.
  • PET Positron Emission Tomography
  • SPECT Single-photon emission computed tomography images
  • ⁇ -amyloid ( ⁇ ) plaques are among the most prevalent pathological characteristics of Alzheimer's disease (AD), which can appear many years before the dementia is diagnosed.
  • AD Alzheimer's disease
  • functional imaging agents makes it possible to assess amyloid deposition in vivo.
  • One promising known radiotracer is Pittsburgh Compound-B (u C-PiB), which binds with high affinity and high specificity to ⁇ plaques. It has been shown that AD patients tend to have higher PiB binding in cortical regions than normal controls.
  • Other important Amyloid imaging compounds are being developed such as Florbetapir, and could also be utilized with the present invention. .
  • a method of determining the degree of uptake of a PET maker in an individual candidate PET scan including the steps of: (a) calculating a series of representative matched controlled PET and MRI templates for a series of controlled sample scans of individuals; (b) computing a series of brain surfaces from the matched templates; (c) aligning the individual candidate PET scan with the templates; (d) aligning the series of brain surfaces with the candidate PET image; (e) selecting a predetermined (M) best candidate templates for each surface location based on a similarity measure between the candidate PET values and the corresponding PET templates; (f) computing M weights for each surface location, utilizing the corresponding MRI templates tissue maps and similarity measures between the candidate PET and the PET templates; (g) utilizing the M weights to combine the corresponding M template tissue indicators to estimate the candidate PET uptake at each location of the average brain surface indicator.
  • the method preferably also includes the step of: (h) combining the average brain surface with the candidate PET scan data to create a combined averaged brain surface for display.
  • the step (c) can comprise utilizing candidate CT or X-Ray scan data in the alignment of the candidate PET images with the series of candidate templates.
  • a method of determining the degree of uptake of an imaging maker in an individual candidate imaging marker scan including the steps of: (a) calculating a series of representative matched controlled imaging marker scans and tissue marker templates for a series of controlled sample scans of individuals; (b) computing a series of internal body delineation surfaces from the matched templates; (c) aligning the individual candidate imaging marker scan with the candidate templates; (d) aligning the individual candidate imaging marker scan with the series of body delineation surfaces; (e) selecting a predetermined (M) best candidate templates for each surface location based on a similarity measure between the candidate imaging marker values and the corresponding controlled imaging marker scans; (f) computing M weights for each surface location, utilizing a corresponding tissue marker map and similarity measures; (g) utilizing the M weights to combine a corresponding M template tissue indicators from corresponding tissue templates into an average brain surface indicator.
  • the imaging marker scans can comprise Positron Emission Tomography (PET) scans or Single-photon emission computed tomography (SPECT).
  • PET Positron Emission Tomography
  • SPECT Single-photon emission computed tomography
  • Each tissue marker template can be calculated from images of different subjects with known image properties.
  • the multiple tissue templates are preferably selected from a wider set of templates in accordance with similar characteristics of the candidate and subjects with known image properties.
  • the templates and candidate images are preferably segmented.
  • a method of determining the brain uptake of an imaging marker in a subject image including the steps of: preparing a series of brain templates from controlled sample images, the templates including co-registering a series of controlled sample images, and creating a probability map containing an approximation of the likelihood that a particular atlas voxel contains grey matter; determining from the brain templates, a correspondence surface between grey and white matter interfaces; for the given subject image, mapping the subject image to a corresponding brain template; and mapping the correspondence in grey matter uptake for the subject image for grey area portions of the brain templates.
  • the controlled sample images can include both PET and MR images.
  • the correspondence can be measured in a predetermined direction relative to the surface between grey and white matter.
  • the mapping can occur for multiple templates.
  • the multiple mappings are preferably combined utilizing a Bayesian network or a weighted sum or voting rules or other fusion techniques.
  • FIG. 1 illustrates schematically one form of operational environment for execution of the preferred embodiment
  • FIG. 2 illustrates a first portion of a flow chart of the steps of the preferred embodiments
  • FIG. 3 illustrates a second portion of a flow chart of the steps involved in the preferred embodiment
  • Fig. 4 illustrates the process of template registration
  • Fig. 5 to Fig. 8 are graphs of mapping results of mapping subjects to template or atlas values; with Fig. 5 showing a comparison of a multi-atlas approach and the single-atlas approaches based on averaged correlation coefficients with the MRI- dependent method. The multi-atlas approach was shown to consistently generate higher correlations for almost all the 104 test subjects.
  • Fig. 6 illustrates a comparison of the multi-atlas approach and the single-atlas approaches based on averaged errors per vertex between the PET and the MRI- dependent methods.
  • the multi-atlas approach consistently generates lower errors for almost all the 104 test subjects.
  • Fig. 7 illustrates a comparison of the proposed multi-atlas approach and the single- atlas approaches based on averaged ROI vertex errors between the PET and the MRI- dependent methods.
  • the multi-atlas approach consistently generates lower errors for all the ROIs.
  • Fig. 9 illustrates an example mapping for an AD patient; and
  • Fig. 10 illustrates an example mapping for a normal patient.
  • a "PET-image-only” method which registers a region of interest (ROI) atlas to a subject's PET images and averages the PiB uptake values within the ROIs.
  • ROI region of interest
  • the estimation accuracy of this method can be dependent on the selection of the atlas and the registration errors. It has been found through the utilization of multiple atlases, improved results are obtained.
  • the embodiments provide a more robust "PET-only" method that improves the posterior probability of the assessment. To achieve this, three major strategies are employed as follows:
  • a tissue probability map is introduced to guide the measurement of the PiB values, instead of the hard ROI partitions copied from a single warped ROI atlas.
  • the probability map is the prior knowledge learned from a training set, therefore incorporating the population variations, and becoming more robust than the ROIs simply obtained from a single atlas image.
  • the utilization of multiple atlases also allows for each PET image to be from a different PET atlas.
  • the use of multiple PET atlases allows for the selection of each location of subject matter in the database to be similar.
  • the method of the second example embodiment can use for a given patient, the templates A,B,C for a pixel in the frontal lobe, and templates C,D,E for a pixel on the temporal lobe.
  • a subject-specific optimal subset of atlases can be selected from a large pool of atlases, and combined by a Bayesian framework to improve the posterior probability of the estimation.
  • the weights to combine the different templates can be varied pixel by pixel.
  • the PiB uptake values are then directly estimated, which avoids the explicit need for segmentation of grey matter. Therefore using multiple atlases statistically reduces the registration and sampling error found in each individual atlas.
  • subject-specific probability maps are also utilized by using nonlocal means segmentation of the subject PET image. This also provides a methodology for computing the weights at each pixel. With multiple atlases, such a segmentation derives the probability map specifically for the particular subject based on population information, and thus improves the estimation of the priors and the posteriors further.
  • the embodiments are able to utilise only PET images, yet still provides a reasonably accurate estimation that has small estimation errors, and high correlations with MRI-based methods.
  • the proposed method has general application for both volume-based and surface-based PiB assessments, a surface based measurement is initially described. A volume-based measurement is relatively simpler and can be conducted similarly without using the surface model.
  • the method provided by the embodiments can be used as a clinic inspection tool for the diagnosis and monitoring of the Alzheimer's disease.
  • the method can be applied to other PET markers of Amyloid (AVI), and is general enough to be applied to any other PET markers for any pathology, and to any other SPECT markers for any pathology.
  • AVI Amyloid
  • Fig. 1 there is illustrated the operational environment 1 for implementation of the preferred embodiments.
  • PET images are scanned 2 for storage in a database 3 for processing.
  • Image analysis system 4 carries out the image analysis method of the preferred embodiments and outputs an image report 5 including a number of measures.
  • N in one embodiment equaled 20
  • representative templates are formed, for test subjects having known degrees of AD.
  • the PET and corresponding MRI images are obtained and aligned.
  • CT scans are available, they can also be matched for the test subjects. From each PET and optional CT scan, a corresponding brain surface is computed.
  • Step 1 The new subject PET is aligned to the N templates, based on the PET scan and utilizing the optional CT scan where available.
  • Step 2 The N template brain surfaces are position relative to the subject PET. Each of the N template surfaces are treated as a surface mesh. For each point on the surface mesh, a comparison is made between the new subject PET value 26 and corresponding PET values 27, 28 at each of the templates, and a difference measure obtained.
  • Step 3 For each surface location, the M best template matches are stored based on the similarity between the new subject PET and the corresponding template PET.
  • Step 4 The M best template matches are used to derive M weights for each surface location. Using the template tissue maps, the M weights are utilized to fuse or weigh together the corresponding PET values to produce an overall PET value. The fusion occurs on a location by location basis.
  • Step 5 The results are displayed on an 'average brain surface', with the average brain surface being derived from a weighting of the template surfaces. With the PET values being displayed on the derived average brain surface 36. Because all the brain templates surfaces are co-registered together the candidate PET can be displayed on anyone of the template surface or on the average surface to represent the population.
  • present medical practice often facilitates the production of a CT type scan along with a PET scan in a combined PET/CT scanner.
  • CT scans are readily available, they are ideally utilized in the registration process.
  • a CT scan does not provide for good tissue delineation, they do provide for very good fluid and bone delineation.
  • a CT scan is available for a new subject, they can be utilized in a number of ways:
  • step 1 the CT scan can be incorporated in aligning the corresponding PET scan with the templates.
  • the CT scan will provide clear bone delineation of the new subject and can therefore be utilized in the alignment process.
  • step 4 given the CT of the patient is available, it is possible to estimate where the grey matter limit is as the CT will delineate the borders of the brain surface. The CT can therefore be utilized in correcting the grey matter calculation for the current PET scan, in border regions and thereby improve overall estimations.
  • each MRI image is spatially normalized to an atlas (in the example embodiment the atlas used was the Collins atlas: Collins, D., Zijdenbos, A., Kollokian, V., Sled, J., Kabani, N., Holmes, C, Evans, A., 1998. Design and construction of a realistic digital brain phantom. IEEE Trans. Med. Imag. 17 (3), 463-468.).
  • Prior probability maps of the main tissues (GM, WM, and CSF) associated with the atlas were also utilized (in our case provided part of SPM with the atlas, Ashburner, J., Friston, K., 1999 "Nonlinear spatial normalization using basis functions" Hum. Brain Mapp. 7 (4), 254-26,).
  • the atlas and associated prior can alternatively be computed easily from any database of images.
  • the MRI image and the PET image are co-registered by a locally rigid transform.
  • the method used can be as disclosed in Ourselin, S., Roche, A., Subsol, G., Pennec, X., Ayache, N., 2001. Reconstructing a 3D structure from serial histological sections. Image Vis. Comput. 19 (1), 25-31.
  • the intensity values of the PET images are normalized by standard uptake value ratio (SUVR) (Lopresti BJ, Klunk WE, Mathis CA, Hoge JA, Ziolko SK. Lu X, et al, "Simplified quantification of Pittsburgh compound B amyloid imaging PET studies: a comparative analysis", J Nucl Med 2005;46: 1959-72Lopresti et al., 2005) was utilised to ensure inter and intra subject comparisons.
  • SUVR is defined as the value of a region containing specific binding to one without specific binding.
  • Cerebellar gray matter is often used as the referenced non-binding region as it is believed to be devoid of senile plaques (Joachim, C, Morris, J., Selkoe, D., 1989. Diffuse senile plaques occur commonly in the cerebellum in Alzheimer's disease. American J. Pathol. 135 (2), 309-319).
  • the cerebellum mask from MRI is used to localize the region in PET image for the normalization. Finally, the interface surface between the gray matter and white matter is extracted from the segmented MRI images for each atlas.
  • This preprocessing step can be as set out in: Fripp J., Bourgeat P., Acosta O., Raniga P., Modat M., Pike E., Jones G., O'Keefe G., Masters L., Ames D., Ellis A., Maruff P., Currie J., Villemagne L., Rowe C, Salvado O., Ourselin S., 2008. Appearance modeling of 11C PiB PET images: characterizing amyloid deposition in Alzheimer's disease, mild cognitive impairment and healthy aging. Neuroimage 43 (3), 430-439.
  • the template preparation proceeds with a starting set of base images which can comprise a series of corresponding MRI and PET scan images for a collection of subjects.
  • a series of separate templates can be created. For each template, their MRI and PET images are co-registered (aligned) rigidly. The tissues are segmented on the template MRI images, and then the grey matter / white matter interfaces are determined. To allow users to inspect the interior cortical areas, the surfaces of the grey/white matter interfaces are separated into left and right hemispheres. Moreover, each template has a grey matter probability map created, which indicates how likely an image voxel belongs to grey matter.
  • the grey matter probability map can be created by standard intensity based segmentation methods using a Gaussian Mixture Model as described in the previous citation of Fripp et al.
  • Template Surface Registration a multi-resolution EM-ICP method is applied to establish the correspondence among different template surfaces of grey/white matter interfaces. After surface registration, the template surfaces are re- sampled in order to share the same number of corresponding vertices.
  • the EM-ICP method can be as set out in: Granger, S., & Pennec, X. (2002), “Multi- scale EM-ICP : A Fast and Robust Approach for Surface Registration", Computer Vision— ECCV 2002, 2353, 418-432 Springer, and Combes, B. and Prima, S., 2010 "An efficient EM- ICP algorithm for symmetric consistent non-linear registration of point sets" Medical Image Computing and Computer- Assisted Intervention (MICCAI), 594—601.
  • MICCAI Medical Image Computing and Computer- Assisted Intervention
  • Registration for PET images an affine / mild deformable registration between PET images of a specific subject and a corresponding template is performed to bring the surface and the probability map from the template space to the subject space.
  • the probability map in the subject space can be generated by the nonlocal means segmentation on the subject PET image.
  • weighting schemes can be used.
  • the M weights can be utilized in a weighted average in combining the corresponding template tissue indicators.
  • Another alternative technique is that provided by a voting algorithm to determine a corresponding template tissue indicator.
  • a Bayesian framework can be utilized as described below.
  • the symbol ⁇ denotes the intersection of the line along the normal direction of a surface vertex v and the PET image I.
  • the symbol / is the tissue label, representing GM, WM and CSF with the values of 1, 2 and 3, respectively.
  • the expectation can be calculated by
  • the probability P ⁇ I,x) — , where ⁇
  • P ⁇ 1 ⁇ A ,l,x) represents the probability for the voxel x to be GM in the transformed template A , which can be obtained from the transformed template probability maps.
  • the probability P ⁇ A ⁇ l,x) measures the probability of the voxel x to be well aligned between the test image I and the transformed template A .
  • N ⁇ x Due to the low resolution of PET images, the size of N ⁇ x) should not be too small, otherwise the resulting mutual information will fit the noise.
  • N ⁇ x was set to be 30x30x30, which covers all the voxels along the line ⁇ . Therefore, P ⁇ A ⁇ l, N( x) ) was constant with respect to the variable x (x E A).
  • Equation (4) shows the additive property for the estimation of the mean PiB retention at each surface vertex: the estimation from multiple atlases can be attained by independent estimation from each single atlas and then linearly combined in a weighted way.
  • the combination weights P ⁇ A ⁇ ⁇ , N( x) ) reflect the alignment between the test image I and the transformed templates A . As the alignment is assessed by local metric, such a combination is nonlinear for the whole surface.
  • This additive property is favourable for the approach when the template set needs to be dynamically determined. It makes the switch of selected templates easy by confining the changes to the affected templates only.
  • Coupled when used in the claims, should not be interpreted as being limited to direct connections only.
  • the terms “coupled” and “connected,” along with their derivatives, may be used. It should be understood that these terms are not intended as synonyms for each other.
  • the scope of the expression a device A coupled to a device B should not be limited to devices or systems wherein an output of device A is directly connected to an input of device B. It means that there exists a path between an output of A and an input of B which may be a path including other devices or means.
  • Coupled may mean that two or more elements are either in direct physical or electrical contact, or that two or more elements are not in direct contact with each other but yet still co-operate or interact with each other.

Abstract

L'invention concerne un procédé pour déterminer le degré d'absorption d'un marqueur de tomographie par émission de positons (TEP) chez un individu candidat pour un balayage TEP, le procédé comprenant les étapes consistant à : (a) calculer une série de modèles IRM et TEP contrôlés correspondants représentatifs pour une série de balayages d'échantillon contrôlés d'individus ; (b) calculer une série de surfaces cérébrales à partir des modèles correspondants ; (c) aligner le balayage TEP de l'individu candidat avec les modèles candidats ; (d) aligner les images TEP candidates avec la série de surfaces cérébrales ; (e) sélectionner (M) meilleurs modèles candidats prédéterminés pour chaque emplacement de surface sur la base d'une mesure de similarité entre les valeurs TEP candidates et les balayages TEP contrôlés correspondants ; (f) calculer des M poids pour chaque emplacement de surface, en utilisant une carte de tissu IRM correspondante ; (g) utiliser les M poids pour combiner M indicateurs de tissu de modèle correspondants à partir des modèles IRM correspondants en un indicateur moyen de surface cérébrale.
PCT/AU2012/001536 2011-12-15 2012-12-14 Procédé et appareil d'évaluation d'images médicales WO2013086580A1 (fr)

Priority Applications (4)

Application Number Priority Date Filing Date Title
US14/365,745 US9361686B2 (en) 2011-12-15 2012-12-14 Method and apparatus for the assessment of medical images
AU2012350363A AU2012350363B2 (en) 2011-12-15 2012-12-14 Method and apparatus for the assessment of medical images
EP12857342.5A EP2790575B1 (fr) 2011-12-15 2012-12-14 Procédé et appareil d'évaluation d'images médicales
CN201280067975.5A CN104093354B (zh) 2011-12-15 2012-12-14 用于评估医学图像的方法和设备

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
AU2011905242A AU2011905242A0 (en) 2011-12-15 Method and apparatus for the assessment of medical images
AU2011905242 2011-12-15

Publications (1)

Publication Number Publication Date
WO2013086580A1 true WO2013086580A1 (fr) 2013-06-20

Family

ID=48611723

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/AU2012/001536 WO2013086580A1 (fr) 2011-12-15 2012-12-14 Procédé et appareil d'évaluation d'images médicales

Country Status (5)

Country Link
US (1) US9361686B2 (fr)
EP (1) EP2790575B1 (fr)
CN (1) CN104093354B (fr)
AU (1) AU2012350363B2 (fr)
WO (1) WO2013086580A1 (fr)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2937039A1 (fr) * 2014-04-25 2015-10-28 Advanced MR Analytics AB Quantification de volume tissulaire maigre
CN105205538A (zh) * 2015-10-14 2015-12-30 清华大学 基于重要性采样的推理算法及神经电路
WO2016009300A1 (fr) * 2014-07-15 2016-01-21 Koninklijke Philips N.V. Test statistique de données d'imagerie comprenant une normalisation stéréotaxique avec une image modèle personnalisée
CN105426958A (zh) * 2015-11-02 2016-03-23 清华大学 通过神经电路实现因果推理的方法和神经电路
US10729919B2 (en) 2016-10-07 2020-08-04 Siemens Healthcare Gmbh Method for supporting radiation treatment planning for a patient
CN113409272A (zh) * 2021-06-21 2021-09-17 上海联影医疗科技股份有限公司 数据分析方法、装置、计算机设备以及可读存储介质

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8977029B2 (en) * 2012-08-24 2015-03-10 Siemens Aktiengesellschaft Method and system for multi-atlas segmentation of brain computed tomography image data
JP6162241B2 (ja) * 2013-07-25 2017-07-12 株式会社日立製作所 Ｘ線ｃｔ装置
JP6703323B2 (ja) * 2015-09-17 2020-06-03 公益財団法人神戸医療産業都市推進機構 生体の画像検査のためのｒｏｉの設定技術
WO2018001099A1 (fr) * 2016-06-30 2018-01-04 上海联影医疗科技有限公司 Procédé et système d'extraction d'un vaisseau sanguin
CL2018001428A1 (es) * 2018-05-28 2018-08-24 Univ Del Desarrollo Un método para procesar imágenes cerebrales.
US10945685B2 (en) * 2018-07-25 2021-03-16 New York University System and method for normalizing standardized uptake values in brain positron emission tomography (PET) images
CN109300124B (zh) * 2018-09-19 2022-04-12 暨南大学 一种基于非人灵长类动物的立体定位pet-mri脑模板建立的方法
TWI697686B (zh) * 2019-06-20 2020-07-01 臺北榮民總醫院 基於磁振造影分析腦組織成分的系統與方法
CN110288641A (zh) * 2019-07-03 2019-09-27 武汉瑞福宁科技有限公司 Pet/ct与mri脑部图像异机配准方法、装置、计算机设备及存储介质
CN115330775B (zh) * 2022-10-13 2023-01-17 佛山科学技术学院 一种脑卒中ct和mri影像征象定量评估方法及系统

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060074290A1 (en) * 2004-10-04 2006-04-06 Banner Health Methodologies linking patterns from multi-modality datasets
WO2008093057A1 (fr) * 2007-01-30 2008-08-07 Ge Healthcare Limited Instruments d'aide au diagnostic de maladies neurodégénératives
US20110129129A1 (en) * 2009-11-30 2011-06-02 General Electric Company System and method for integrated quantifiable detection, diagnosis and monitoring of disease using population related data for determining a disease signature

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6740883B1 (en) * 1998-08-14 2004-05-25 Robert Z. Stodilka Application of scatter and attenuation correction to emission tomography images using inferred anatomy from atlas
US7324842B2 (en) * 2002-01-22 2008-01-29 Cortechs Labs, Inc. Atlas and methods for segmentation and alignment of anatomical data
WO2004040437A1 (fr) * 2002-10-28 2004-05-13 The General Hospital Corporation Analyse par imagerie de troubles dans des tissus
US7873405B2 (en) * 2004-06-02 2011-01-18 Siemens Medical Solutions Usa, Inc. Automated detection of Alzheimer's disease by statistical analysis with positron emission tomography images
CN101068498A (zh) * 2004-10-04 2007-11-07 旗帜健康公司 链接来自多模态数据集的图案的方法
BRPI0619257A2 (pt) * 2005-11-30 2011-09-27 Nihon Mediphysics Co Ltd método de detecção de doença neurodegenerativa, programa de detecção e detector
WO2008107809A2 (fr) * 2007-03-06 2008-09-12 Koninklijke Philips Electronics, N.V. Diagnostic et alignement automatisés, complétés par une estimation de flux tep/rm.
WO2008155682A1 (fr) * 2007-06-21 2008-12-24 Koninklijke Philips Electronics N.V., Diagnostic différentiel de la démence, basé sur un modèle, et réglage interactif du taux de signification
US8553961B2 (en) * 2008-08-04 2013-10-08 Koninklijke Philips N.V. Automatic pre-alignment for registration of medical images
US20100074480A1 (en) * 2008-09-22 2010-03-25 University Of Washington Device for generating alternative of normal brain database
EP2347711A4 (fr) * 2008-09-22 2013-03-13 Nihon Mediphysics Co Ltd Dispositif de création de base de données de cerveau normal différent
US9788753B2 (en) * 2009-02-26 2017-10-17 Ramot At Tel-Aviv University Ltd. Method and system for characterizing cortical structures

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060074290A1 (en) * 2004-10-04 2006-04-06 Banner Health Methodologies linking patterns from multi-modality datasets
WO2008093057A1 (fr) * 2007-01-30 2008-08-07 Ge Healthcare Limited Instruments d'aide au diagnostic de maladies neurodégénératives
US20110129129A1 (en) * 2009-11-30 2011-06-02 General Electric Company System and method for integrated quantifiable detection, diagnosis and monitoring of disease using population related data for determining a disease signature

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
See also references of EP2790575A4 *
THOMPSON, P. ET AL.: "Mapping Cortical Change in Alzheimer's Disease, Brain Development, and Schizophrenia", NEUROIMAGE, vol. 23, 2004, pages S2 - S18, XP004609072 *

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106233332A (zh) * 2014-04-25 2016-12-14 先进穆阿分析公司 瘠瘦组织体积量化
WO2015162120A1 (fr) * 2014-04-25 2015-10-29 Advanced Mr Analytics Ab Quantification du volume de tissu maigre
US9996926B2 (en) 2014-04-25 2018-06-12 Advanced Mr Analytics Ab Lean tissue volume quantification
EP2937039A1 (fr) * 2014-04-25 2015-10-28 Advanced MR Analytics AB Quantification de volume tissulaire maigre
KR101858382B1 (ko) 2014-04-25 2018-05-15 어드밴스드 엠알 애널리틱스 에이비 제지방 조직 부피 정량화
WO2016009300A1 (fr) * 2014-07-15 2016-01-21 Koninklijke Philips N.V. Test statistique de données d'imagerie comprenant une normalisation stéréotaxique avec une image modèle personnalisée
US10269115B2 (en) 2014-07-15 2019-04-23 Koninklijke Philips N.V. Imaging data statistical testing including a stereotactical normalization with a personalized template image
CN105205538A (zh) * 2015-10-14 2015-12-30 清华大学 基于重要性采样的推理算法及神经电路
CN105205538B (zh) * 2015-10-14 2018-08-28 清华大学 基于重要性采样的推理算法及神经电路
CN105426958A (zh) * 2015-11-02 2016-03-23 清华大学 通过神经电路实现因果推理的方法和神经电路
US10729919B2 (en) 2016-10-07 2020-08-04 Siemens Healthcare Gmbh Method for supporting radiation treatment planning for a patient
CN113409272A (zh) * 2021-06-21 2021-09-17 上海联影医疗科技股份有限公司 数据分析方法、装置、计算机设备以及可读存储介质
CN113409272B (zh) * 2021-06-21 2023-04-28 上海联影医疗科技股份有限公司 数据分析方法、装置、计算机设备以及可读存储介质

Also Published As

Publication number Publication date
CN104093354B (zh) 2017-06-09
AU2012350363B2 (en) 2018-01-18
EP2790575B1 (fr) 2017-06-14
EP2790575A1 (fr) 2014-10-22
US20140307936A1 (en) 2014-10-16
AU2012350363A1 (en) 2014-07-03
CN104093354A (zh) 2014-10-08
EP2790575A4 (fr) 2015-12-30
US9361686B2 (en) 2016-06-07

Similar Documents

Publication Publication Date Title
US9361686B2 (en) Method and apparatus for the assessment of medical images
Roy et al. Robust skull stripping using multiple MR image contrasts insensitive to pathology
Udupa et al. A framework for evaluating image segmentation algorithms
JP5695648B2 (ja) 医用画像処理方法および装置
Dupont et al. Fully-integrated framework for the segmentation and registration of the spinal cord white and gray matter
Zhou et al. MR-less surface-based amyloid assessment based on 11C PiB PET
US8682051B2 (en) Smoothing of dynamic data sets
Le Pogam et al. Evaluation of a 3D local multiresolution algorithm for the correction of partial volume effects in positron emission tomography
CN112435341B (zh) 三维重建网络的训练方法及装置、三维重建方法及装置
WO2011119935A2 (fr) Systèmes et procédés de traitement tractographique amélioré
Gong et al. Nonrigid image registration using spatially region-weighted correlation ratio and GPU-acceleration
US9020215B2 (en) Systems and methods for detecting and visualizing correspondence corridors on two-dimensional and volumetric medical images
US20150363951A1 (en) Systems and methods for objective tractographic processing using features of grid structures of the brain
US20090069665A1 (en) Automatic Lesion Correlation in Multiple MR Modalities
US20230341914A1 (en) Generating reformatted views of a three-dimensional anatomy scan using deep-learning estimated scan prescription masks
Gupta et al. A hybrid framework for registration of carotid ultrasound images combining iconic and geometric features
Pai et al. Evaluation of fiber bundles across subjects through brain mapping and registration of diffusion tensor data
Dore et al. CapAIBL: automated reporting of cortical PET quantification without need of MRI on brain surface using a Patch-Based method
Longuefosse et al. Lung CT Synthesis Using GANs with Conditional Normalization on Registered Ultrashort Echo-Time MRI
WO2017198518A1 (fr) Dispositif de traitement de données d'image
Tang et al. Validation of mutual information-based registration of CT and bone SPECT images in dual-isotope studies
Zhou et al. MR-less surface-based amyloid estimation by subject-specific atlas selection and Bayesian fusion
Wang et al. Spatial attention-based implicit neural representation for arbitrary reduction of MRI slice spacing
Xia et al. Image imputation in cardiac MRI and quality assessment
Han et al. α-Information-Based Registration of Dynamic Scans for Magnetic Resonance Cystography

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 12857342

Country of ref document: EP

Kind code of ref document: A1

REEP Request for entry into the european phase

Ref document number: 2012857342

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 14365745

Country of ref document: US

ENP Entry into the national phase

Ref document number: 2012350363

Country of ref document: AU

Date of ref document: 20121214

Kind code of ref document: A